save_harness

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It discloses the destructive 'overwrite' nature and the requirement that harness_data must include harness_id and revision_id from the loaded harness, indicating a versioned save. It lacks details on error behavior or side effects, but covers the critical overwrite aspect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action. The first sentence states the function, the second provides essential usage instructions. No superfluous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (mutation, dependency on prior load), the description provides the necessary workflow and prerequisites. No output schema exists, but the description sufficiently focuses on the input requirements. Minor gaps like error conditions or return values do not significantly impair usability.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the two parameters, but the description adds crucial meaning by specifying that harness_data must contain harness_id and revision_id from the loaded harness. This goes beyond the schema's generic 'Complete WorkingHarness JSON object' and clarifies the required internal structure and provenance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Save (overwrite) a legacy harness' with a specific verb and resource. It distinguishes from siblings like create_harness by emphasizing 'overwrite' and 'legacy', and the usage note about get_harness sets it apart as a follow-up update operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit workflow guidance: 'Use get_harness first to load current state, modify it, then save.' This clarifies when to use this tool relative to get_harness and implicitly against create_harness. However, it doesn't explicitly state exclusions (e.g., not for new harnesses), so a slight deduction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.